© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46007
    Prev
    Next
    INDEX
    Explanations

    Mount Doom, Pleasant Baptist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ター
    0.73
    cą
    0.66
    बु
    0.66
    ூரில்
    0.65
    pun
    0.64
    स्क
    0.63
    ク
    0.63
    sea
    0.62
    ू
    0.61
    coord
    0.60
    POSITIVE LOGITS
    ه
    0.88
    ö
    0.87
    é
    0.84
    ó
    0.82
    ires
    0.64
    .
    0.64
    u
    0.63
    عين
    0.62
     or
    0.61
    ية
    0.61
    Activations Density 0.000%

    No Known Activations